An Improved Class of Estimators for Finite Population Mean in Sample Surveys

Abstract

This paper proposes a class of estimators for estimating the finite population mean Y of a study variate y using information on two auxiliary variates, one of which is positively and the other negatively correlated with the study variate y. An asymptotically optimum estimator (AOE) in the class is identified with its bias and mean square error formulae. It is observed that the proposed AOE is more efficient than SRIVASTAVA (1965), SRIVASTAVA (1974), PRASAD (1989) and GANDGE, VARGHESE, and PRABHU-AJGAONKAR (1993) estimators.